• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.11-22
• /
• 2010

This paper is a study on implementation of intelligent image surveillance system using context information and supplements temporal-spatial constraint, the weak point in which it is hard to process it in real time. In this paper, we propose scene analysis algorithm which can be processed in real time in various environments at low resolution video(320*240) comprised of 30 frames per second. The proposed algorithm gets rid of background and meaningless frame among continuous frames. And, this paper uses wavelet transform and edge histogram to detect shot boundary. Next, representative key-frame in shot boundary is selected by key-frame selection parameter and edge histogram, mathematical morphology are used to detect only motion region. We define each four basic contexts in accordance with angles of feature points by applying vertical and horizontal ratio for the motion region of detected object. These are standing, laying, seating and walking. Finally, we carry out scene analysis by defining simple context model composed with general context and emergency context through estimating each context's connection status and configure a system in order to check real time processing possibility. The proposed system shows the performance of 92.5% in terms of recognition rate for a video of low resolution and processing speed is 0.74 second in average per frame, so that we can check real time processing is possible.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.4
• /
• pp.825-840
• /
• 2015

Adaptive bitrate (ABR) streaming technology has become an important and prevalent feature in many multimedia delivery systems, with content providers such as Netflix and Amazon using ABR streaming to increase bandwidth efficiency and provide the maximum user experience when channel conditions are not ideal. Where such systems could see improvement is in the delivery of live video with a closed loop cognitive control of video encoding. In this paper, we present streaming camera system which provides spatially and temporally adaptive video streams, learning the user's preferences in order to make intelligent scaling decisions. The system employs a hardware based H.264/AVC encoder for video compression. The encoding parameters can be configured by the user or by the cognitive system on behalf of the user when the bandwidth changes. A cognitive video client developed in this study learns the user's preferences(i.e. video size over frame rate) over time and intelligently adapts encoding parameters when the channel conditions change. It has been demonstrated that the cognitive decision system developed has the ability to control video bandwidth by altering the spatial and temporal resolution, as well as the ability to make scaling decisions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.521-529
• /
• 2020

Forest fires are one of the most important environmental risks that have adverse effects on many aspects of life, such as the economy, environment, and health. The early detection, quick prediction, and rapid response of forest fires can play an essential role in saving property and life from forest fire risks. For the rapid discovery of forest fires, there is a method using meteorological data obtained from local sensors installed in each area by the Meteorological Agency. Meteorological conditions (e.g., temperature, wind) influence forest fires. This study evaluated a Data Mining (DM) approach to predict the burned area of forest fires. Five DM models, e.g., Stochastic Gradient Descent (SGD), Support Vector Machines (SVM), Decision Tree (DT), Random Forests (RF), and Deep Neural Network (DNN), and four feature selection setups (using spatial, temporal, and weather attributes), were tested on recent real-world data collected from Gyeonggi-do area over the last five years. As a result of the experiment, a DNN model using only meteorological data showed the best performance. The proposed model was more effective in predicting the burned area of small forest fires, which are more frequent. This knowledge derived from the proposed prediction model is particularly useful for improving firefighting resource management.

• Development and Reproduction
• /
• v.20 no.4
• /
• pp.297-304
• /
• 2016

Lectins belong to the pattern-recognition receptors (PRRs) class and play important roles in the recognition and elimination of pathogens via the innate immune system. Recently, it was reported that lily-type lectin-1 is involved when a pathogen attacks in the early immune response of fish. However, this study is limited to information that the lectin is involved in the innate immune response against viral infection. In the present study, the lily-type lectin-2 and -3 of Oplegnathus fasciatus (OfLTL-2 and 3) have been presented to be included B-lectin domain and two D-mannose binding sites in the amino acid sequence that an important feature for the fundamental structure. To investigate the functional properties of OfLTLs, the tissue distribution in the healthy rock bream and temporal expression during early developmental stage analysis are performed using quantitative real-time PCR. OfLTL-2 and 3 are predominantly expressed in the liver and skin, but rarely expressed in other organ. Also, the transcripts of OfLTLs are not expressed during the early developmental stage but its transcripts are increased after immune-related organs which are fully formed. In the challenge experiment with RBIV (rock bream iridovirus), the expression of OfLTLs was increased much more strongly in the late response than the early, unlike previously known. These results suggest that OfLTLs are specifically expressed in the immune-related tissues when those organs are fully formed and it can be inferred that the more intensively involved in the second half to the virus infection.

• Cartoon and Animation Studies
• /
• s.49
• /
• pp.677-696
• /
• 2017

Cartoons and consequently animation are an effective way of visualizing futuristic scenarios. Here we look at how animation is becoming ubiquitous and an integral part of this future today: the cybernetic and mediated society that we are being transformed into. Animation therefore becomes a form of speech between humans and this networked reality, either as an interface or as representation that gives temporal form to objects. Animation or specifically animated films usually are associated with character based short and feature films, fiction or nonfiction. However animation is not constricted to traditional cinematic formats and language, the same way that design and communication have become treated as separate fields, however according to $Vil{\acute{e}}m$ Flusser they aren't. The same premise can be applied to animation in a networked culture: Animation has become an intrinsic to design processes and products - as in motion graphics, interface design and three-dimensional visualization. Video-games, virtual reality, map based apps and social networks constitute layers of an expanded universe that embodies our network based culture. They are products of design and media disciplines that are increasingly relying on animation as a universal language suited to multi-cultural interactions carried in digital ambients. In this sense animation becomes a discourse, the same way as Roland Barthes describes myth as a type of speech. With the objective of exploring the role of animation as a design tool, the proposed research intends to develop transmedia creative visual strategies using animation both as narrative and as an user interface.

• Journal of Veterinary Clinics
• /
• v.26 no.6
• /
• pp.650-654
• /
• 2009

A 1-week-old, male Korean native calf with acute clinical signs of depression, mild diarrhea, ataxia, recumbency and tremor was referred to Chonbuk Veterinary Medical Center of Chonbuk National University. Vision loss and cornea edema were also observed on physical examination. The patient had been deteriorated with nystagumus, strabisumus and opisthtonus. Blood cell count test and blood biochemistry test revealed remarkable leukocytosis, and hypoalbuminemia and increased blood urea nitrogen. No remarkable findings were observed on radiography. On magnetic resonance imaging study, there were enlarge lateral, third, and forth ventricles. The cortical grey and subcortical white matter of left temporal lobe showed hypointense on T1-weighted images and hyperintense on T2-weighted images, and slightly enhanced on contrast-enhanced T1-weighted images. Escherichia coli strain was identified from cerebrospinal fluid sample. Palliative treatment was attempted but the neonatal calve was expired three days after admission. Severe multifocal fibrino-suppurative meningitis with Escherichia coli infection was confirmed histopathologically.

• Atmosphere
• /
• v.29 no.5
• /
• pp.671-687
• /
• 2019

This study evaluates the long-term seasonal predictability of summer (June, July and August) heatwaves over South Korea using 30-year (1989~2018) Hindcast data of the Pusan National University Coupled General Circulation Model (PNU CGCM)-Weather Research and Forecasting (WRF) chain. Heatwave indices such as Number of Heatwave days (HWD), Heatwave Intensity (HWI) and Heatwave Warning (HWW) are used to explore the long-term seasonal predictability of heatwaves. The prediction skills for HWD, HWI, and HWW are evaluated in terms of the Temporal Correlation Coefficient (TCC), Root Mean Square Error (RMSE) and Skill Scores such as Heidke Skill Score (HSS) and Hit Rate (HR). The spatial distributions of daily maximum temperature simulated by WRF are similar overall to those simulated by NCEP-R2 and PNU CGCM. The WRF tends to underestimate the daily maximum temperature than observation because the lateral boundary condition of WRF is PNU CGCM. According to TCC, RMSE and Skill Score, the predictability of daily maximum temperature is higher in the predictions that start from the February and April initial condition. However, the PNU CGCM-WRF chain tends to overestimate HWD, HWI and HWW compared to observations. The TCCs for heatwave indices range from 0.02 to 0.31. The RMSE, HR and HSS values are in the range of 7.73 to 8.73, 0.01 to 0.09 and 0.34 to 0.39, respectively. In general, the prediction skill of the PNU CGCM-WRF chain for heatwave indices is highest in the predictions that start from the February and April initial condition and is lower in the predictions that start from January and March. According to TCC, RMSE and Skill Score, the predictability is more influenced by lead time than by the effects of topography and/or terrain feature because both HSS and HR varies in different leads over the whole region of South Korea.

• The Journal of the Korea Contents Association
• /
• v.20 no.1
• /
• pp.617-629
• /
• 2020

In the historical and cultural blocks with the most concentrated urban cultural heritage, the development of both side streets is impacted by the development of the main street, which shows a gradual decline. The loss of placeness on both side streets has resulted in more empty houses. Therefore, it is urgent to pay attention and take countermeasures to the empty houses in historical and cultural blocks. In this study, the vacant houses on Zhongshan Road in Hangzhou, China were taken as the object of study to understand the location theory and the six dimensions of Matthew Carmona's urban design. Meanwhile, it further analyzed the evaluative features of the placeness of the vacant houses in the historical and cultural street, to provide direction and basis for the flexible using of other empty houses in Zhongshan Road. Then by applying the Analytic Hierarchy Process (AHP), it obtained the importance scale of each evaluative feature and compared the evaluation results of experts with the analysis results of cases, getting the results as follows: In the flexible application of vacant houses in historical and cultural street, the evaluation result of placeness indicates that this kind of usage should be in order of societal level, perceptional level, functional level, morphological level, visual hierarchy and temporal level; among the evaluative features, security, identity, usability, individuality, aesthetics, connection, diversity, openness, continuity, accessibility, order and history should be considered in turn.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.10
• /
• pp.1422-1432
• /
• 1993

Nonlinear mapping function of the HCNN( Hidden Control Neural Network ) can change over time to model the temporal variability of a speech signal by combining the nonlinear prediction of conventional neural networks with the segmentation capability of HMM. We have two things in this paper. first, we showed that the performance of the HCNN is better than that of HMM. Second, the HCNN with its prediction error measure given by weighted distance is proposed to use suitable distance measure for the HCNN, and then we showed that the superiority of the proposed system for speaker-independent speech recognition tasks. Weighted distance considers the differences between the variances of each component of the feature vector extraced from the speech data. Speaker-independent Korean digit recognition experiment showed that the recognition rate of 95%was obtained for the HCNN with Euclidean distance. This result is 1.28% higher than HMM, and shows that the HCNN which models the dynamical system is superior to HMM which is based on the statistical restrictions. And we obtained 97.35% for the HCNN with weighted distance, which is 2.35% better than the HCNN with Euclidean distance. The reason why the HCNN with weighted distance shows better performance is as follows : it reduces the variations of the recognition error rate over different speakers by increasing the recognition rate for the speakers who have many misclassified utterances. So we can conclude that the HCNN with weighted distance is more suit-able for speaker-independent speech recognition tasks.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.6
• /
• pp.627-639
• /
• 2014

In respect of the nutrients cycling in coastal environment, regeneration in bottom layer is one of major source of nutrients. We analyzed the bottom water quality at the 14 stations during 9 years from 2004 to 2012 to investigate the characteristics of nutrients at bottom layer in Jinhae Bay. Concentrations of DIN, DIP and DSi showed the large seasonal variation and were higher in summer. Especially, average concentrations of these nutrients were two times higher in hypoxic season than in normoxic season. In summer, high concentrations of DIN, DIP and DSi caused by regeneration were common feature, but spatial distribution of DSi differ from that of DIN and DIP. DIN and DIP were higher in Masan Bay, while DSi was higher in Masan Bay as well as in center of Jinhae Bay. In comparison with DIN and DIP, DSi was significantly affected by nutrients regeneration at bottom layer in whole season. According to time series analysis, DIN concentration was decreased from approximately $14{\mu}M$ to $6{\mu}M$. This result induce that Si:N ratio at bottom layer in Jinhae Bay changed from approximately 1 to 3.